Xuyang Liu
12 papers · 2023–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🌍 Conference Polyglot · Silver 🗺️ Taxonomy Completionist (28) 🏆 Keyword Champion (4) 💎 Century Club · Bronze
🗃️
Keyword Collector
(65)
⚡
Prolific Year · Productive
Venues
Top co-authors
Research topics
Machine Learning
(9)
Artificial Intelligence
(8)
Deep Learning
(8)
Application Areas
(7)
Core AI
(7)
Models
(4)
Computer Vision
(3)
Optimization & Theory · Machine Learning
(3)
Architectures
(2)
Learning Types · Machine Learning
(2)
Learning Types · Deep Learning
(2)
Optimization & Theory · Deep Learning
(2)
Healthcare & Medicine
(1)
Reinforcement Learning
(1)
Analysis
(1)
Keywords
token compression
(4)
reinforcement learning
(2)
visual token
(2)
inference acceleration
(2)
computational efficiency
(2)
vision-language model
(2)
autonomous driving
(1)
multimodal learning
(1)
benchmark evaluation
(1)
parameter-efficient transfer learning
(1)
parameter efficient
(1)
visual recognition
(1)
sequence optimization
(1)
image recognition
(1)
video generation
(1)
multimodal large language model
(1)
model adaptation
(1)
downstream task
(1)
dense prediction
(1)
pre-trained model
(1)
Papers
Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
CVPR 2026
Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration
AAAI 2026
Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
AAAI 2026
GUI-G²: Gaussian Reward Modeling for GUI Grounding
AAAI 2026
Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving
CVPR 2026
Structure-based RNA Design by Step-wise Optimization of Latent Diffusion Model
AAAI 2026
Variation-aware Vision Token Dropping for Faster Large Vision-Language Models
CVPR 2026
Accelerating Diffusion Transformers with Token-wise Feature Caching
ICLR 2025
Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers
ICLR 2025
Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models
EMNLP 2025
V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark
NeurIPS 2024
CCQ: Cross-Class Query Network for Partially Labeled Organ Segmentation
AAAI 2023